VERSION-SPECIFIC RISK PROFILES

Model Doom Scores

Compare the assessed risk profile of each source-verified model version. Scores combine capability, autonomy, deployment, misuse potential, and remaining control difficulty on the same 0 to 100 meaning as the Doom Index.

Comparison, not double counting.

Model scores do not directly move the news-driven Doom Index. A launch or evaluation affects the main index only through its separately sourced evidence item.

CompanyOrder16 models

92.9OpenAIGPT-5.6 Sol 86.8OpenAIGPT-5.6 Terra 83.8AnthropicClaude Opus 4.8 82.0AnthropicClaude Fable 5 81.7AnthropicClaude Mythos 5 81.6SpaceXAIGrok 4.5 80.9OpenAIGPT-5.5 80.6OpenAIGPT-5.6 Luna 79.7AnthropicClaude Sonnet 5 79.4OpenAIGPT-5.5 Pro 75.4MetaMuse Glimmer 30B 74.2AnthropicClaude Opus 4 67.3DeepSeekDeepSeek-R1 66.7AnthropicClaude Sonnet 4 65.5Google DeepMindGemini Robotics 1.5 51.4OpenAIGPT-4

Accessible model score and dimension comparison
Model	Company	Doom Score	Capability	Autonomy	Deployment	Misuse	Control difficulty
GPT-5.6 Sol	OpenAI	92.9	98	96	92	94	82
GPT-5.6 Terra	OpenAI	86.8	91	89	98	84	72
Claude Opus 4.8	Anthropic	83.8	93	92	75	84	68
Claude Fable 5	Anthropic	82.0	91	90	75	83	65
Claude Mythos 5	Anthropic	81.7	96	92	22	96	84
Grok 4.5	SpaceXAI	81.6	88	84	87	78	68
GPT-5.5	OpenAI	80.9	88	86	82	76	68
GPT-5.6 Luna	OpenAI	80.6	84	82	98	75	65
Claude Sonnet 5	Anthropic	79.7	89	90	94	62	58
GPT-5.5 Pro	OpenAI	79.4	92	87	58	78	70
Muse Glimmer 30B	Meta	75.4	66	72	95	70	82
Claude Opus 4	Anthropic	74.2	83	78	76	66	62
DeepSeek-R1	DeepSeek	67.3	74	45	88	66	65
Claude Sonnet 4	Anthropic	66.7	78	65	82	56	48
Gemini Robotics 1.5	Google DeepMind	65.5	72	82	38	60	64
GPT-4	OpenAI	51.4	64	32	68	48	42